Annual Review of Biomedical Data Science - Early Publication

Biomedicine has rapidly digitized over recent decades, from genomic sequencing to electronic medical records. Now, the rise of large language models (LLMs) is driving a generative artificial intelligence (AI) revolution in natural language processing (NLP). Together, these trends create unprecedented possibilities to optimize patient care and accelerate biomedical discovery. Biomedical NLP already boosts productivity by automating labor-intensive tasks such as knowledge extraction and medical abstraction. Emerging approaches promise creativity gain, surpassing standard healthcare practices and uncovering emergent capabilities through Web-scale biomedical knowledge and population-level patient data. However, LLMs remain prone to hallucinations and omissions, and ensuring compliance and safety is vital in order to do no harm. Incorporating diverse modalities such as imaging and genomics is also essential for comprehensive solutions. We review these challenges and opportunities in biomedical NLP, offering historical context, surveying the current state of the art, and exploring frontiers for AI researchers and biomedical practitioners.

The TITAN-X Precision Medicine Platform was engineered to rapidly, fully, and efficiently utilize large-scale immunology datasets, including public data, in drug discovery and development. TITAN-X integrates big data with artificial intelligence (AI), bioinformatics, and advanced computational modeling to seamlessly transition from early target discovery to clinical testing of new therapeutics, developing biomarker-driven precision medicines tailored to specific patient populations. We illustrate the capabilities of TITAN-X through four case studies, demonstrating its use in computationally driven target discovery; characterization of novel immunometabolic mechanisms in infectious, inflammatory, and autoimmune diseases; and identification of biomarker signatures for patient stratification in clinical trials designed to maximize therapeutic efficacy and safety. Data-driven and AI-powered approaches like TITAN-X are enhancing the pace of drug development, reducing costs, tailoring treatments, and increasing the probability of success in clinical trials.

Generative artificial intelligence (AI) has had a profound impact on biomedicine and health, both in professional work and in education. Based on large language models (LLMs), generative AI has been found to perform as well as humans in simulated situations taking medical board exams, answering clinical questions, solving clinical cases, applying clinical reasoning, and summarizing information. Generative AI is also being used widely in education, performing well in academic courses and their assessments. This review summarizes the successes of LLMs and highlights some of their challenges in the context of education, most notably aspects that may undermines the acquisition of knowledge and skills for professional work. It then provides recommendations for best practices to overcome the shortcomings of LLM use in education. Although there are challenges for the use of generative AI in education, all students and faculty, in biomedicine and health and beyond, must have understanding and be competent in its use.

The growth of electronic health record (EHR) databases in size and availability has created an unprecedented opportunity to better understand human health and disease. However, conducting robust EHR studies requires careful filtering criteria and study design, as EHRs pose several challenges that can confound analyses and lead to inaccurate results. Here we review these challenges and make suggestions about how to avoid or adjust for major confounders and biases in common EHR study designs. We further highlight qualities of EHR data that make different diseases more or less feasible for study. These recommendations for conducting research using EHRs will help inform database selection, improve reproducibility of results across the field, and enhance the validity of study results.

Efforts to mitigate bias and enhance fairness in the artificial intelligence (AI) community have predominantly focused on technical solutions. While numerous reviews have addressed bias in AI, this review uniquely focuses on the practical limitations of technical solutions in healthcare settings, providing a structured analysis across five key dimensions affecting their real-world implementation: who defines bias and fairness, which mitigation strategy to use and prioritize among dozens that are inconsistent and incompatible, when in the AI development stages the solutions are most effective, for which populations, and the context for which the solutions are designed. We illustrate each limitation with empirical studies focusing on healthcare and biomedical applications. Moreover, we discuss how value-sensitive AI, a framework derived from technology design, can engage stakeholders and ensure that their values are embodied in bias and fairness mitigation solutions. Finally, we discuss areas that require further investigation and provide practical recommendations to address the limitations covered in the study.

Pharmaceutical research and development largely depend on the quantity and quality of data that are available to support projects. The secondary use of data by means of collaborative and integrative approaches is yielding promising results in drug safety research. However, there are challenges that must be overcome in these integrative approaches, such as interoperability issues, intellectual property protection, and, in the case of clinical information, personal data safeguards. The OMOP common data model and the EHDEN and DARWIN EU platforms constitute successful examples of data sharing initiatives in the clinical domain, while the eTOX, eTRANSAFE, and VICT3R international projects are examples of corporate data sharing in toxicology research. The VICT3R project is using these shared data for generating virtual control groups to be applied in nonclinical drug safety assessment. Drug-related knowledge bases that integrate information from different sources also constitute useful tools in the drug safety domain.

The increased capabilities of generative artificial intelligence (AI) have dramatically expanded its possible use cases in medicine. We provide a comprehensive overview of generative AI use cases for clinicians, patients, clinical trial organizers, researchers, and trainees. We then discuss the many challenges—including maintaining privacy and security, improving transparency and interpretability, upholding equity, and rigorously evaluating models—that must be overcome to realize this potential, as well as the open research directions they give rise to.

Artificial intelligence (AI) methods were first developed nearly seven decades ago. Only in recent years have they demonstrated their potential to improve clinical care at the bedside. AI systems are now capable of interpreting, predicting, and even generating important medical information. AI medical devices share many similarities with traditional medical devices but also diverge from them in important ways. Despite widespread optimism and enthusiasm surrounding the use of such devices to improve care processes, patient outcomes, and the healthcare experience for patients, caregivers, and clinicians alike, little evidence exists so far for their effectiveness in practice. Even less is known about the safety or equity of AI medical devices. As with any new technology, this exciting time is accompanied by appropriate questions regarding if, how much, when, and who such AI systems really help. Different stakeholders, ranging from patients to clinicians to industry device developers, may have divergent preferences or assessments of risk and benefits, warranting an informed public discussion to guide emerging regulatory efforts. This review summarizes the rapidly evolving recent efforts and evidence related to the regulation and evaluation of AI medical devices and highlights opportunities for future work to ensure their effectiveness, safety, and equity.

Tabular medical datasets, like electronic health records (EHRs), biobanks, and structured clinical trial data, are rich sources of information with the potential to advance precision medicine and optimize patient care. However, real-world medical datasets have limited patient diversity and cannot simulate hypothetical outcomes, both of which are necessary for equitable and effective medical research. Fueled by recent advancements in machine learning, generative models offer a promising solution to these data limitations by generating enhanced synthetic data. This review highlights the potential of conditional generative models (CGMs) to create patient-specific synthetic data for a variety of precision medicine applications. We survey CGM approaches that tackle two medical applications: correcting for data representation biases and simulating digital health twins. We additionally explore how the surveyed methods handle modeling tabular medical data and briefly discuss evaluation criteria. Finally, we summarize the technical, medical, and ethical challenges that must be addressed before CGMs can be effectively and safely deployed in the medical field.